Applying traditional post-hoc attribution methods to segmentation or object detection
predictors offers only limited insights, as the obtained feature attribution maps at input level …

The performance of semantic segmentation of remote sensing images (RSIs) heavily
depends on the number of pixel-level annotations. In practice, the accumulation of pixel …

We propose the concept of error-reversing autoencoders (ERA) for correcting pixel-wise
errors made by an arbitrary semantic segmentation model. For this, we reframe the …

In the emerging field of video coding for machines, video datasets with pristine video quality
and high-quality annotations are required for a comprehensive evaluation. However …

Failures in autonomous systems are inevitable. In applications such as autonomous driving,
such failures can have critical consequences. Failure prediction is a potential solution. In this …

Semantic segmentation is the process of assigning a label to every pixel in the image.
Current state-of-the-art segmentation models becoming unnecessarily large and …